fairfolio
Saved Projects

A Smart AI Driven Tool for ADHD Featuring a Large Language Model to Detect Conversational Markers For a More Accurate, Early Diagnosis

CSEF · 2023 Behavioral & Social Sciences Second Award

Reddy Megha, Reddy Neha · 11

Overview

Today, attention-deficit/hyperactivity disorder (ADHD) is one of the most commonly misdiagnosed disorders. While ADHD is greatly overdiagnosed in many areas, those in vulnerable communities do not have access to the proper resources to receive the diagnosis they need. Current clinical evaluations are prone to misdiagnosis as they rely on qualitative observations of perceived behavior. This method alone is highly inefficient, and can have devastating effects on long-term health as a result of unnecessary prescriptions. The objective of this project was to create an accurate and efficient tool for ADHD diagnosis aimed at combating the prevalent issue of ADHD over diagnosis while providing more accessibility to those in vulnerable communities. In this research, a large language model (LLM) was used to extract conversational markers common in individuals with ADHD, and several machine learning classifiers were then applied to classify the data into three metrics of evaluation: inattention, hyperactivity, and impulsivity. The algorithm was trained using a dataset composed of over 15,000 data points and generates a prediction with an overall accuracy of 0.894 in the three metrics. A real-time scoring model is applied to combine the individual scores from a scale of 0-10 to get a final score ranging from 0-30, where 0 indicates no markers of ADHD present, and 30 indicates the highest number of ADHD markers present. The prediction generated by the model can be used in conjunction with a psychiatrist’s evaluation to provide a more confident, and accurate diagnosis.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

Competition history

  • CSEF 2023 Behavioral & Social Sciences · Entry S0423

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google